CMR-Agent: Learning a Cross-Modal Agent for Iterative Image-to-Point Cloud Registration

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yao, Gongxin, Xuan, Yixin, Li, Xinyang, Pan, Yu
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916346610057216
author Yao, Gongxin
Xuan, Yixin
Li, Xinyang
Pan, Yu
author_facet Yao, Gongxin
Xuan, Yixin
Li, Xinyang
Pan, Yu
contents Image-to-point cloud registration aims to determine the relative camera pose of an RGB image with respect to a point cloud. It plays an important role in camera localization within pre-built LiDAR maps. Despite the modality gaps, most learning-based methods establish 2D-3D point correspondences in feature space without any feedback mechanism for iterative optimization, resulting in poor accuracy and interpretability. In this paper, we propose to reformulate the registration procedure as an iterative Markov decision process, allowing for incremental adjustments to the camera pose based on each intermediate state. To achieve this, we employ reinforcement learning to develop a cross-modal registration agent (CMR-Agent), and use imitation learning to initialize its registration policy for stability and quick-start of the training. According to the cross-modal observations, we propose a 2D-3D hybrid state representation that fully exploits the fine-grained features of RGB images while reducing the useless neutral states caused by the spatial truncation of camera frustum. Additionally, the overall framework is well-designed to efficiently reuse one-shot cross-modal embeddings, avoiding repetitive and time-consuming feature extraction. Extensive experiments on the KITTI-Odometry and NuScenes datasets demonstrate that CMR-Agent achieves competitive accuracy and efficiency in registration. Once the one-shot embeddings are completed, each iteration only takes a few milliseconds.
format Preprint
id arxiv_https___arxiv_org_abs_2408_02394
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle CMR-Agent: Learning a Cross-Modal Agent for Iterative Image-to-Point Cloud Registration
Yao, Gongxin
Xuan, Yixin
Li, Xinyang
Pan, Yu
Computer Vision and Pattern Recognition
Robotics
Image-to-point cloud registration aims to determine the relative camera pose of an RGB image with respect to a point cloud. It plays an important role in camera localization within pre-built LiDAR maps. Despite the modality gaps, most learning-based methods establish 2D-3D point correspondences in feature space without any feedback mechanism for iterative optimization, resulting in poor accuracy and interpretability. In this paper, we propose to reformulate the registration procedure as an iterative Markov decision process, allowing for incremental adjustments to the camera pose based on each intermediate state. To achieve this, we employ reinforcement learning to develop a cross-modal registration agent (CMR-Agent), and use imitation learning to initialize its registration policy for stability and quick-start of the training. According to the cross-modal observations, we propose a 2D-3D hybrid state representation that fully exploits the fine-grained features of RGB images while reducing the useless neutral states caused by the spatial truncation of camera frustum. Additionally, the overall framework is well-designed to efficiently reuse one-shot cross-modal embeddings, avoiding repetitive and time-consuming feature extraction. Extensive experiments on the KITTI-Odometry and NuScenes datasets demonstrate that CMR-Agent achieves competitive accuracy and efficiency in registration. Once the one-shot embeddings are completed, each iteration only takes a few milliseconds.
title CMR-Agent: Learning a Cross-Modal Agent for Iterative Image-to-Point Cloud Registration
topic Computer Vision and Pattern Recognition
Robotics
url https://arxiv.org/abs/2408.02394